Research map / Video / Video generation
MSEditor: Toward Consistent Multi-Shot Video Editing
Kunyu Feng, Yue Ma, Bingyuan Wang, Yuefeng Wang, Zhiyuan Qin, Hao Cheng, Hao Li, Qifeng Chen, Zeyu Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Cross-Shot Packing strategy (ablation) | MSEditor · multi-shot editing benchmark | Inter-shot subject consistency: 0.8919 -> 0.9370 | Improved |
| add Cross-Shot Packing strategy (ablation) | MSEditor · multi-shot editing benchmark | Shot semantic consistency: 0.1521 -> 0.1886 | Improved |
| add Sparse Cross Attention for per-shot text (ablation) | MSEditor · multi-shot editing benchmark | Shot semantic consistency: 0.1432 -> 0.1886 | Improved |
| add Sparse Cross Attention (ablation) | MSEditor · multi-shot editing benchmark | Aesthetic Score: 5.70 -> 6.05 | Improved |
| add first-frame editing (ablation) | MSEditor · multi-shot editing benchmark | Inter-shot subject consistency: 0.9321 -> 0.9370 | Improved |
| MSEditor vs VACE retrained on same multi-shot data | MSEditor · multi-shot editing benchmark | Intra-shot subject consistency: 0.9057 -> 0.9501 | Improved |
| retrain VACE on multi-shot dataset (ablation) | VACE · multi-shot editing benchmark | Inter-shot subject consistency: 0.9237 -> 0.9301 | Improved |
| MSEditor vs best single-shot baseline VACE (Aesthetic) | MSEditor · multi-shot editing benchmark | Aesthetic Score: 5.91 -> 6.05 | Improved |
Closest papers by meaning
- VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling (NeurIPS 2026 · similarity 0.88)
- VidToMe: Video Token Merging for Zero-Shot Video Editing (CVPR 2024 · similarity 0.87)
- Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists (NeurIPS 2025 · similarity 0.87)
- FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing (AAAI 2025 · similarity 0.87)
- CCEdit: Creative and Controllable Video Editing via Diffusion Models (CVPR 2024 · similarity 0.87)
- VEU-Bench: Towards Comprehensive Understanding of Video Editing (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
